Word2Vec is a popular algorithm based on: Efficient Estimation of Word Representations in Vector Space, Mikolov et. al (2013). Training on a single corpus the algorithm will generate one multidimensional vector for each word. These vectors are known to have symantic meanings. A commonly used distance measure is cosine similarity. This implementation is based on the word2vec port available at: https://github.com/allenai/Word2VecJava